Alex Cockrean

This update to the branch predictors (both Perceptron and Generic) replaces the hashmap that was previously being used to keep previous-state information between predict and update with a queue (called...

Given it also has inter-unit buffers, should the in-order core also be updated to check for branches in these buffers and flush the branchPredictor if required? _Originally posted by @FinnWilkinson...

Updates how a LoopBuffer is begun; and how branch mispredicts are determined by the execute units. This was motivated by the incorrect misprediction calculation in the execute. However, doing so...

Changes to BP in dev mean that the feedback to it comes from the Writeback unit, not the execution units. Therefore, the core model diagram in the docs should be...

Tage

1

Adding a TAGE branch predictor. Performance relative to previous best (Perceptron) summarised below: Benchmark | BP_update time | BP_update mispredict | TAGE time | TAGE mispredict | Performance change (percentage)...

**Problem Description** Currently the front-end gets prediction from BP instantaneously from the fetch unit. In reality, predictions aren't instantaneous, and the point at which a branch get's it's prediction varies...

**Problem Description** Implement output of a file listing the config options for a given SimEng run. In particular this file should specify where SimEng has used default config options in...